rubber-ducking SKILL.md skillA

rubber-ducking from andrewbrown-usda/aigb-skills-usda is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add andrewbrown-usda/aigb-skills-usda/rubber-ducking@v1

Pins v1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
andrewbrown-usda/aigb-skills-usda
Path
skills/rubber-ducking/SKILL.md
Versions recorded
5
Latest version
v1, committed Oct 9, 2026
First version recorded
Sep 25, 2026
Size
7,307 bytes
Repository stars
7
License
a license file GitHub does not identify

Interactive guided walkthrough of code, line by line, where the agent reflects back your explanations without analysis. Use when debugging, reviewing, or understanding code by forced articulation.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Rubber Ducking

Explain your code out loud. Your brain fills in gaps when reading silently. Speaking makes you confront every line. That's where bugs surface.

Saying it aloud -- to anyone, even a rubber duck -- works because:
- You slow down and notice what you skip.
- You explain *why* each line exists, not just what it does.
- Hearing yourself exposes the gap between what you think and what's actually there.

Research shows 50-90% of bugs surface during this walkthrough, often before the listener says anything. The listener barely matters. The act of explaining is everything.

## When to Use

Use rubber-ducking to find bugs by explaining code aloud.

Also works for:
- Reviewing unfamiliar code
- Learning a new codebase
- Documenting assumptions before tests

Skip it if:
- Code is working fine
- Your bug is an API misunderstanding (use `/research` instead)
- You need automated code review (use `/code-review`)

---

## Quick Start

Invoke the skill and provide your code:

```
/rubber-ducking

Paste the code you want to walk through. Optionally, specify the language (e.g., Python, JavaScript, R) or the specific issue you're investigating.
```

**Example**:
```
/rubber-ducking
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add andrewbrown-usda/aigb-skills-usda/rubber-ducking@sha256:d434f32ad71c4481

The line at the top of this page pins the label v1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dmcvjqt5pqd4xlm4.svg)](https://markdownregistry.com/a/art_dmcvjqt5pqd4xlm4)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 25, 2026 and Oct 9, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
v1 latest2026-10-09 0d32dbb 7,307 BA view · diff
v12026-10-02 da773d3 7,307 BA view · diff
v12026-10-02 8c813e9 7,284 BA view · diff
v12026-09-30 b8f4ba9 7,419 BA view · diff
v12026-09-25 160ae7c 7,221 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7307 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

andrewbrown-usda/aigb-skills-usda · 7 stars · license a license file GitHub does not identify · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dmcvjqt5pqd4xlm4
GET https://markdownregistry.com/api/v1/resolve?ref=andrewbrown-usda/aigb-skills-usda/rubber-ducking
GET https://markdownregistry.com/api/v1/blob/d434f32ad71c4481f8a9342e7dbd54073eff6ede0efca5db4ffa55fe841e19e8

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from andrewbrown-usda/aigb-skills-usda

AGENTS.md AGENTS.md file
andrewbrown-usda/aigb-skills-usda · AGENTS.md
git:20261014.40ca2a1 · audit A · 7 stars
adr-distillation SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/adr-distillation/SKILL.md · Distills enduring architectural decisions and design rationale from wave orchestration plans or historical git changes…
v1.0.0 · audit A · 7 stars
agent-onboarding SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/agent-onboarding/SKILL.md · Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when…
v1 · audit A · 7 stars
apply-fed-oss-license SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/apply-fed-oss-license/SKILL.md · Audit and update an arbitrary codebase to follow the Code.mil federal open-source licensing model (MIT with 17 U.S.C…
v1.0.0 · audit A · 7 stars
arcpy-migration SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/arcpy-migration/SKILL.md · Migrates ArcPy and ArcGIS Pro workflows to explicit, testable open-source Python geospatial workflows. Use when…
v1 · audit A · 7 stars
caveman SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/caveman/SKILL.md · Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra…
git:20261014.9719148 · audit A · 7 stars
code-review-2axis SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/code-review-2axis/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code…
git:20261014.d4e89ae · audit A · 7 stars
conventional-commits SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/conventional-commits/SKILL.md · Create, classify, validate, and explain commit messages using Conventional Commits v1.0.0, with repository-aware type…
v1 · audit A · 7 stars
copilot-history-briefing SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/copilot-history-briefing/SKILL.md · Reads Copilot conversation history and extracts executive-ready success stories. Use when the user asks to study prior…
v1.3 · audit A · 7 stars
deep-investigative-research SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/deep-investigative-research/SKILL.md · Comprehensive investigation of complex multi-domain narratives (technology, theology, policy, finance). Systematically…
v1 · audit A · 7 stars
doc-consistency SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/doc-consistency/SKILL.md · Normalizes documentation and examples for consistency in style, format, and accuracy. Ensures code matches existing…
v1 · audit A · 7 stars
dr-lexus SKILL.md skill
andrewbrown-usda/aigb-skills-usda · skills/dr-lexus/SKILL.md · Plain language directive. Cuts verbosity, corporate jargon, and overused AI vocabulary. Use when you want clear…
v1 · audit A · 7 stars

Every file in andrewbrown-usda/aigb-skills-usda

Browse by kind, by grade A, or by owner.